报告题目：Solving differential equations using neural networks

报告人：金邦梯 教授 （香港中文大学）

报告时间：5月19日（周一）下午 4:00-5:00

报告地点：理科楼数学系A304

摘要: Solving partial differential equations using neural networks has received a lot of recent attention, due to its tremendous potential in the high-dimensional case. In this talk, I shall present our recent efforts for two classes of boundary value problems, which may contain singularities or non-self adjoint operators. I will present the numerical algorithms, discuss the convergence analysis, and illustrate the algorithms with numerical experiments.

报告人简介：Bangti Jin is a Professor of Mathematics(Global STEM Scholar) at the Chinese Univeristy of Hong Kong. He received a Ph.D in Mathematics from the Chinese University of Hong Kong in 2008. Previously, he was Lecturer and Reader, and Professor at Department of Computer Science, University College London, an assistant professor of Mathematics at the University of California, Riverside, a visiting assistant professor at Texas A&M University, an Alexandre von Humboldt Postdoctoral Researcher at University of Bremen. His research intreasts include computational inverse problems, numerical analysis, machine learning, and scientific computing.

邀请人：陈俊清